Matches in SemOpenAlex for { <https://semopenalex.org/work/W2959245800> ?p ?o ?g. }
Showing items 1 to 79 of
79
with 100 items per page.
- W2959245800 abstract "In some tasks (e.g., assigning meanings to ambiguous words) humans produce multiple distinct alternatives in response to a particular stimulus, apparently mirroring the environmental probabilities associated with each alternative. For this purpose, a network architecture is needed that can produce a distribution of outcomes, and a learning algorithm is needed that can lead to the discovery of ensembles of connection weights that reproduce the environmentally specified probabilities. Stochastic symmetric networks such as Boltzmann machines and networks that use graded activations perturbed with Gaussian noise can exhibit such distributions at equilibrium, and they can be trained to match environmentally specified probabilities using Contrastive Hebbian Leaning, the generalized form of the Boltzmann Learning algorithm. Learning distributions exacts a considerable computational cost as processing time is used both in settling to equilibrium and in sampling equilibrium statistics. The work presented here examines the extent of this cost and how it may be minimized, and produces speed-ups of roughly a factor of 5 compared to previously published results." @default.
- W2959245800 created "2019-07-23" @default.
- W2959245800 creator A5020224649 @default.
- W2959245800 creator A5046113734 @default.
- W2959245800 date "2019-05-23" @default.
- W2959245800 modified "2023-09-26" @default.
- W2959245800 title "Tractable Learning of Probability Distributions Using the Contrastive Hebbian Algorithm" @default.
- W2959245800 cites W95629291 @default.
- W2959245800 doi "https://doi.org/10.4324/9781315789354-142" @default.
- W2959245800 hasPublicationYear "2019" @default.
- W2959245800 type Work @default.
- W2959245800 sameAs 2959245800 @default.
- W2959245800 citedByCount "0" @default.
- W2959245800 crossrefType "book-chapter" @default.
- W2959245800 hasAuthorship W2959245800A5020224649 @default.
- W2959245800 hasAuthorship W2959245800A5046113734 @default.
- W2959245800 hasConcept C105795698 @default.
- W2959245800 hasConcept C111437709 @default.
- W2959245800 hasConcept C11413529 @default.
- W2959245800 hasConcept C119857082 @default.
- W2959245800 hasConcept C121332964 @default.
- W2959245800 hasConcept C121864883 @default.
- W2959245800 hasConcept C144024400 @default.
- W2959245800 hasConcept C149441793 @default.
- W2959245800 hasConcept C154945302 @default.
- W2959245800 hasConcept C163716315 @default.
- W2959245800 hasConcept C189645446 @default.
- W2959245800 hasConcept C192576344 @default.
- W2959245800 hasConcept C193999330 @default.
- W2959245800 hasConcept C33923547 @default.
- W2959245800 hasConcept C41008148 @default.
- W2959245800 hasConcept C46312422 @default.
- W2959245800 hasConcept C50644808 @default.
- W2959245800 hasConcept C62520636 @default.
- W2959245800 hasConceptScore W2959245800C105795698 @default.
- W2959245800 hasConceptScore W2959245800C111437709 @default.
- W2959245800 hasConceptScore W2959245800C11413529 @default.
- W2959245800 hasConceptScore W2959245800C119857082 @default.
- W2959245800 hasConceptScore W2959245800C121332964 @default.
- W2959245800 hasConceptScore W2959245800C121864883 @default.
- W2959245800 hasConceptScore W2959245800C144024400 @default.
- W2959245800 hasConceptScore W2959245800C149441793 @default.
- W2959245800 hasConceptScore W2959245800C154945302 @default.
- W2959245800 hasConceptScore W2959245800C163716315 @default.
- W2959245800 hasConceptScore W2959245800C189645446 @default.
- W2959245800 hasConceptScore W2959245800C192576344 @default.
- W2959245800 hasConceptScore W2959245800C193999330 @default.
- W2959245800 hasConceptScore W2959245800C33923547 @default.
- W2959245800 hasConceptScore W2959245800C41008148 @default.
- W2959245800 hasConceptScore W2959245800C46312422 @default.
- W2959245800 hasConceptScore W2959245800C50644808 @default.
- W2959245800 hasConceptScore W2959245800C62520636 @default.
- W2959245800 hasLocation W29592458001 @default.
- W2959245800 hasOpenAccess W2959245800 @default.
- W2959245800 hasPrimaryLocation W29592458001 @default.
- W2959245800 hasRelatedWork W1526606941 @default.
- W2959245800 hasRelatedWork W1755468095 @default.
- W2959245800 hasRelatedWork W2050681940 @default.
- W2959245800 hasRelatedWork W2100553090 @default.
- W2959245800 hasRelatedWork W2162542068 @default.
- W2959245800 hasRelatedWork W2255802415 @default.
- W2959245800 hasRelatedWork W2274595687 @default.
- W2959245800 hasRelatedWork W2521827923 @default.
- W2959245800 hasRelatedWork W2554954837 @default.
- W2959245800 hasRelatedWork W2622155583 @default.
- W2959245800 hasRelatedWork W2741878218 @default.
- W2959245800 hasRelatedWork W2753839018 @default.
- W2959245800 hasRelatedWork W2943476805 @default.
- W2959245800 hasRelatedWork W2964031514 @default.
- W2959245800 hasRelatedWork W2981322253 @default.
- W2959245800 hasRelatedWork W3045080532 @default.
- W2959245800 hasRelatedWork W3169578542 @default.
- W2959245800 hasRelatedWork W3174436986 @default.
- W2959245800 hasRelatedWork W3187685774 @default.
- W2959245800 hasRelatedWork W789121818 @default.
- W2959245800 isParatext "false" @default.
- W2959245800 isRetracted "false" @default.
- W2959245800 magId "2959245800" @default.
- W2959245800 workType "book-chapter" @default.